feat(fs): add directory listing seam

This commit is contained in:
Yichen Jiang
2026-07-03 14:36:20 +08:00
parent d8ea99756d
commit 803ed4bd95
15 changed files with 268 additions and 23 deletions

View File

@@ -30,7 +30,7 @@ The read-before-write/edit and observed-state policy is a fourth package, `@deep
The first backend is deliberately local-only: `dsh-fs-local` implements `ctx.fs` against the host filesystem. Future sibling backends can provide sandboxed, remote, virtual, or project-scoped filesystems behind the same interface.
The first consumer is deliberately text-file-only: `dsh-tool-fs` exposes model-facing `read`, `write`, and `edit` tools for UTF-8 text files. Future consumers can add directory listing, search/glob, binary-safe operations, file watching, or higher-level project operations without changing the local backend package, as long as the needed capability exists on `ctx.fs`.
The first model-facing consumer is deliberately text-file-only: `dsh-tool-fs` exposes model-facing `read`, `write`, and `edit` tools for UTF-8 text files. The provider seam also includes direct directory listing (`listDir`) so non-model-facing consumers such as skill discovery can enumerate roots through `ctx.fs` without importing `node:fs`; future consumers can add search/glob, binary-safe operations, file watching, or higher-level project operations without changing the local backend package, as long as the needed capability exists on `ctx.fs`.
Filesystem permissions and sandboxing are not implied by this split. The local backend resolves relative paths from its configured base directory, but containment policy is a separate decision: either a stricter `ctx.fs` implementation enforces it, or a permission/sandbox plugin wraps `tools/execute` and vetoes calls before they reach the consumer.
@@ -57,9 +57,10 @@ The root `tool-fs` plugin registers the full filesystem tool suite (`read`, `wri
`@deepseek-ai/dsh-fs` owns a semantic filesystem service. It is higher-level than `readFile` / `writeFile` so `tool-fs` does not reimplement path resolution, versioning, text decoding, binary rejection, pagination, atomic replacement, symlink behavior, or literal edit semantics.
The exact TypeScript signatures are implementation details for the PR, but the interface must cover four semantic operations:
The exact TypeScript signatures are implementation details for the PR, but the interface must cover five semantic operations:
- Resolve a model/plugin-supplied path into a backend-defined target.
- Stat and list target metadata without reading file contents.
- Read a bounded UTF-8 text page from a target.
- Create or replace a UTF-8 text file.
- Edit an existing UTF-8 text file by literal replacement.
@@ -82,6 +83,8 @@ Resolved targets must expose at least three concepts:
Read and mutation results must include an opaque file `version`. A local backend can use mtime/size or a hash-like token; a remote backend can use a revision id. `ctx.fs` records versions in its file-state store for stale checks; consumers may display related metadata but must not interpret the version token.
`listDir` lists direct directory children in stable name order and returns child names, types, resolved child targets, and cheap metadata (`version` and regular-file `size` when available) without opening file contents. Missing directories report `FS_NOT_FOUND`, non-directory targets report `FS_NOT_DIRECTORY`, permission failures report `FS_PERMISSION_DENIED`, and other backend listing failures report `FS_IO_ERROR`.
The provider hands back decoded text: `readText` returns a whole regular text file, `streamText` streams the same text semantics for large files. Both own regular-file checks, bounded line/output handling is NOT theirs — line windowing, numbered-line rendering, and total-line accounting live in the executor (`dsh-tool-fs`), which reads through `ctx.fs` and renders the model-facing window. The provider owns UTF-8 decoding and binary/NUL rejection; it does not know about line windows or views.
Observed-state recording is not on `ctx.fs`: after a successful read the executor emits `fs/observed`, and the `dsh-fs-policy` plugin records `{ version }` for the deriving owner. There is no `full`/`partial` view — a read at any window records the version, and freshness (not view completeness) authorizes a later write/edit.
@@ -92,7 +95,7 @@ Literal edit is a provider primitive (`editText`), not composed in `tool-fs` fro
The policy plugin, not `ctx.fs`, gates on prior observation: an `edit` requires a prior observation by the owner (else `FS_NOT_OBSERVED`), and the recorded version is passed to `editText` as the CAS basis. With the policy plugin absent, `ctx.fs` alone is a complete unconstrained seam (unconditional write/edit); the tool is never method-coupled to the policy.
Filesystem contract failures are thrown as `FsError extends HarnessError`, and the tool registry converts them into `isError` tool results with structured `{ name, code }` metadata. `dsh-fs` owns this vocabulary rather than each tool inventing messages. The codes are `FS_NOT_FOUND`, `FS_NOT_TEXT`, `FS_STALE_VERSION`, `FS_NOT_OBSERVED`, `FS_NOT_REGULAR_FILE`, `FS_AMBIGUOUS_EDIT`, `FS_EDIT_NOT_FOUND`, and `FS_ABORTED`. (An earlier draft included `FS_PARTIAL_OBSERVATION`; freshness-based authorization has no partial/full distinction, so it was dropped.)
Filesystem contract failures are thrown as `FsError extends HarnessError`, and the tool registry converts them into `isError` tool results with structured `{ name, code }` metadata. `dsh-fs` owns this vocabulary rather than each tool inventing messages. The codes are `FS_NOT_FOUND`, `FS_NOT_DIRECTORY`, `FS_NOT_TEXT`, `FS_NOT_REGULAR_FILE`, `FS_PERMISSION_DENIED`, `FS_IO_ERROR`, `FS_STALE_VERSION`, `FS_NOT_OBSERVED`, `FS_AMBIGUOUS_EDIT`, `FS_EDIT_NOT_FOUND`, and `FS_ABORTED`. (An earlier draft included `FS_PARTIAL_OBSERVATION`; freshness-based authorization has no partial/full distinction, so it was dropped.)
## Tool consumer behavior

View File

@@ -39,6 +39,7 @@ abstract resolve(path: string): Promise<FsTarget>
abstract stat(target: FsTarget, signal?: AbortSignal): Promise<FsInfo | undefined>
abstract readText(target: FsTarget, signal?: AbortSignal): Promise<string>
abstract streamText(target: FsTarget, signal?: AbortSignal): Promise<AsyncIterable<string>>
abstract listDir(target: FsTarget, signal?: AbortSignal): Promise<FsDirEntry[]>
abstract writeText(target: FsTarget, content: string, expected: FsWriteIntent, signal?: AbortSignal): Promise<FsWriteOutcome>
abstract editText(target: FsTarget, edit: FsEditRequest, expected: { version: FsVersion }, signal?: AbortSignal): Promise<FsEditOutcome>
@@ -48,12 +49,20 @@ interface FsInfo {
size?: number
}
interface FsDirEntry {
name: string
type: 'file' | 'directory' | 'other'
target: FsTarget
version?: FsVersion
size?: number
}
type FsWriteIntent =
| { kind: 'createIfAbsent' }
| { kind: 'replaceIfVersion'; version: FsVersion }
```
`stat` returns metadata, not content. `version` is the freshness token; `type` lets the executor reject directories/special files before reading; `size` lets the `read` tool choose `readText` vs `streamText` without probing by failure. `undefined` means absent.
`stat` returns metadata, not content. `version` is the freshness token; `type` lets the executor reject directories/special files before reading; `size` lets the `read` tool choose `readText` vs `streamText` without probing by failure. `undefined` means absent. `listDir` returns direct children in stable name order with child names, types, resolved targets, and cheap metadata only; it does not read file contents.
`readText` reads the whole regular text file. `streamText` streams the same text semantics for large files. Both provider primitives own regular-file checks, UTF-8 decoding, binary/NUL rejection, and `FS_NOT_TEXT`; the policy layer never handles raw bytes or reimplements cross-chunk decoding. `readText` is the small-file/direct whole-file primitive, while large model-facing reads use `streamText`.
@@ -107,7 +116,7 @@ It keeps the interface/implementation/consumer discipline, consumer-never-import
## Acceptance Criteria
- `dsh-fs` exposes exactly `resolve`/`stat`/`readText`/`streamText`/`writeText`/`editText`; `stat` returns `FsInfo | undefined`; `writeText` uses `FsWriteIntent` (`createIfAbsent` or `replaceIfVersion`); removed types/primitives are gone, and the old `applyEdit` API is replaced by `editText`.
- `dsh-fs` exposes exactly `resolve`/`stat`/`readText`/`streamText`/`listDir`/`writeText`/`editText`; `stat` returns `FsInfo | undefined`; `listDir` returns stable direct-child metadata without reading contents; `writeText` uses `FsWriteIntent` (`createIfAbsent` or `replaceIfVersion`); removed types/primitives are gone, and the old `applyEdit` API is replaced by `editText`.
- `dsh-fs-policy` adds the observed-state + `read`/`write`/`edit` freshness policy and has HMR/disposal coverage. (It does so as a gate PLUGIN on the `fs/*` events with no `ctx.fileContext` service, per [the event-gate RFC](../architecture/2026-06-26-file-context-as-event-gate.md) — the original service form this RFC proposed was reworked.)
- `dsh-tool-fs` reaches the policy decisions and model-facing schemas stay byte-for-byte unchanged; the observation contract (a read records observed-state; a direct `ctx.fs` read does not) is documented and tested. (The tool injects `fs` and dispatches the `fs/*` events rather than injecting a `fileContext` service, per the event-gate RFC.)
- Windowed read authorizing edit is shown to fail on the pre-refit code and pass after the refit. Existing version-CAS behavior is preserved with a regression test; it is not claimed as a pre-refit failure. An edit based on a stale read must report `FS_STALE_VERSION` before attempting literal matching.